Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to monetary amounts expressed in billions or trillions over specific time frames

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.91
    ****************
    -0.70
    uum
    -0.65
    ":[
    -0.64
    Journal
    -0.64
    UE
    -0.64
    YA
    -0.63
    Motion
    -0.62
    UES
    -0.62
    女
    -0.62
    POSITIVE LOGITS
    hang
    1.02
    loading
    1.00
    priced
    0.99
    lord
    0.98
    valued
    0.96
    whelming
    0.95
    payment
    0.94
    clock
    0.94
    charge
    0.93
    drive
    0.91
    Act Density 0.088%

    No Known Activations